--- title: Perplexity: Sonar Deep Research | Text Generation | ModelsLab description: Build with Perplexity: Sonar Deep Research API by Perplexity. Text generation, chat, code, and reasoning. Pay-per-use. Free tier. url: https://modelslab.com/models/perplexity/perplexity-sonar-deep-research/api.md canonical: https://modelslab.com/models/perplexity/perplexity-sonar-deep-research/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T03:52:55.195309Z --- Perplexity: Sonar Deep Research --- [LLMs.txt](https://modelslab.com/models/open_router/perplexity-sonar-deep-research/llms.txt) [.md](https://modelslab.com/models/perplexity/perplexity-sonar-deep-research.md) perplexity-sonar-deep-research perplexity Closed Source Model $5.000000 / call Perplexity: Sonar Deep Research --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### Perplexity: Sonar Deep Research perplexity perplexity-sonar-deep-research Copy model ID PricingInput $2.00 / 1M tokens Output $8.00 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [ML](https://modelslab.com/models/together_ai/meta-llama-Llama-2-7b-chat-hf)[Together AI](https://modelslab.com/models/together_ai) [meta-llama/Llama-2-7b-chat-hf Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Llama-2-7b-chat-hf) [ZG](https://modelslab.com/models/open_router/z-ai-glm-5v-turbo)[Open Router](https://modelslab.com/models/open_router) [Z.ai: GLM 5V Turbo Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-5v-turbo) [CV](https://modelslab.com/models/together_ai/deepcogito-cogito-v1-preview-qwen-32B)[Together AI](https://modelslab.com/models/together_ai) [Cogito V1 Preview Qwen 32B Closed Source Model](https://modelslab.com/models/together_ai/deepcogito-cogito-v1-preview-qwen-32B) [ML](https://modelslab.com/models/open_router/meta-llama-llama-guard-4-12b)[Open Router](https://modelslab.com/models/open_router) [Meta: Llama Guard 4 12B Closed Source Model](https://modelslab.com/models/open_router/meta-llama-llama-guard-4-12b) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-coder-flash)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 Coder Flash Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-coder-flash) [G2](https://modelslab.com/models/together_ai/google-gemma-2-9b-it)[Together AI](https://modelslab.com/models/together_ai) [Gemma 2 9B It Closed Source Model](https://modelslab.com/models/together_ai/google-gemma-2-9b-it) [Q0](https://modelslab.com/models/together_ai/Qwen-Qwen3-0.6B-Base)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 0.6B Base Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-0.6B-Base) [OG](https://modelslab.com/models/open_router/openai-gpt-4.1-mini)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4.1 Mini Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4.1-mini) [NN](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8)[Together AI](https://modelslab.com/models/together_ai) [Nvidia Nemotron 3 Super 120B A12b Fp8 Closed Source Model](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.1 70B Instruct Turbo Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo) [DV](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2)[Together AI](https://modelslab.com/models/together_ai) [Deepseek V3.2 Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2) [Q2](https://modelslab.com/models/qwen/Qwen-Qwen2.5-Coder-32B-Instruct)[ModelsLab](https://modelslab.com/models/qwen) [Qwen 2.5 Coder 32B Instruct Closed Source Model](https://modelslab.com/models/qwen/Qwen-Qwen2.5-Coder-32B-Instruct) [W2](https://modelslab.com/models/open_router/microsoft-wizardlm-2-8x22b)[Open Router](https://modelslab.com/models/open_router) [WizardLM-2 8x22B Closed Source Model](https://modelslab.com/models/open_router/microsoft-wizardlm-2-8x22b) [RS](https://modelslab.com/models/open_router/undi95-remm-slerp-l2-13b)[Open Router](https://modelslab.com/models/open_router) [ReMM SLERP 13B Closed Source Model](https://modelslab.com/models/open_router/undi95-remm-slerp-l2-13b) [QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-397b-a17b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3.5 397B A17B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-397b-a17b) [SL](https://modelslab.com/models/open_router/sao10k-l3.3-euryale-70b)[Open Router](https://modelslab.com/models/open_router) [Sao10K: Llama 3.3 Euryale 70B Closed Source Model](https://modelslab.com/models/open_router/sao10k-l3.3-euryale-70b) [ML](https://modelslab.com/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)[ModelsLab](https://modelslab.com/models/meta) [Meta Llama 3.1 8B Instruct Turbo Closed Source Model](https://modelslab.com/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 30B A3B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b) About Perplexity: Sonar Deep Research --- Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers... ### Technical Specifications Model IDperplexity-sonar-deep-researchCategoryLLM ModelsTaskText GenerationPrice$5.000000 per million tokensAddedFebruary 20, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate Perplexity: Sonar Deep Research into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "perplexity-sonar-deep-research", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` View the [full API documentation](https://modelslab.com/models/perplexity/perplexity-sonar-deep-research/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Perplexity: Sonar Deep Research API costs $5.000000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Perplexity](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Perplexity: Sonar Deep Research FAQ --- ### What is Perplexity: Sonar Deep Research? Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers... ### How do I use the Perplexity: Sonar Deep Research API? You can integrate Perplexity: Sonar Deep Research into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "perplexity-sonar-deep-research" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Perplexity: Sonar Deep Research cost? Perplexity: Sonar Deep Research costs $5.000000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Perplexity: Sonar Deep Research model ID? The model ID for Perplexity: Sonar Deep Research is "perplexity-sonar-deep-research". Use this ID in your API requests to specify this model. ### Does Perplexity: Sonar Deep Research have a free tier? Yes, ModelsLab offers a free tier that lets you try Perplexity: Sonar Deep Research and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-04-15*